<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />
	<component name="tikaExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.TikaExtractor">
		<property name="maxCompressionRatio">2</property>
		<property name="maxUncompressionSize">10000000</property>
	</component>

                tikaExtractor.setMaxSymbolTermSize(getMaxSymbolTermSize());
                tikaExtractor.setReplaceDuplication(isDuplicateTermRemoved());
                tikaExtractor.setSpaceChars(getSpaceChars());
            }
        } catch (final ComponentNotFoundException e) {
            if (logger.isDebugEnabled()) {

        ResponseData responseData = new ResponseData();
        Map<String, Object> dataMap = new HashMap<>();

        responseData.getMetaDataMap().put(TikaExtractor.class.getSimpleName(), new TikaExtractor());

        String content = " Test Content ";
        assertEquals("Test Content", documentHelper.getContent(null, responseData, content, dataMap));
    }

        if (extractor == null) {
            extractor = ComponentUtil.getComponent("tikaExtractor");
            if (extractor == null) {
                throw new FessSystemException("Could not find tikaExtractor.");
            }
        }

        if (logger.isDebugEnabled()) {
            logger.debug("url={}, extractor={}", responseData.getUrl(), extractor);

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.impl.TikaExtractor;
import org.codelibs.fess.crawler.serializer.DataSerializer;
import org.codelibs.fess.crawler.transformer.impl.AbstractTransformer;
import org.codelibs.fess.crawler.util.CrawlingParameterUtil;